agentleFS
robinbrilrobinbril/claude-code-harness/skills/code-audit/SKILL.md

code-audit

Skill3 starsChanged 23 days agoMITView on GitHub

Full code review of a branch, diff or commit with open-code-review: OCR picks the files and rules, the agent reviews. Use for an audit or a complete review. Requires the `ocr` CLI.

  • Installs packages

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use database-security, malware-analysis and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JeremyMorganSkill

    database-security

    Examines all database interactions for injection, access control, encryption, and data-exposure risks. Use when auditing database and data-layer security.

    Also in 3 projects that use this

  • tsaleSkill

    malware-analysis

    Professional malware analysis workflow for PE executables and suspicious files. Triggers on file uploads with requests like "analyze this malware", "analyze this sample", "what does this executable do", "check this file for malware", or any request to examine suspicious files. Performs static analysis, threat intelligence triage, behavioral inference, and produces analyst-grade reports with reasoned conclusions.

    Also in 3 projects that use this

  • jefflesterSkill

    api-security

    API security best practices and common vulnerability prevention. Enforces security checks for authentication, input validation, SQL injection, XSS, and OWASP Top 10 vulnerabilities. Use when building or modifying APIs.

    Also in 3 projects that use this

  • QiuChenlySkill

    reverse-engineering

    专业二进制逆向工程分析技能。使用IDA Pro MCP工具分析二进制文件、反编译代码、识别漏洞、理解程序逻辑。当用户要求分析可执行文件、反汇编、逆向工程、漏洞挖掘、恶意软件分析时使用此技能。

    Also in 3 projects that use this

  • SentrySkill

    ui-design

    Also in 3 projects that use this

  • GitHubSkill

    refactor

    Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start met /code-audit. Upstream: alibaba/open-code-review at 23992511c8876f51c1a31e52938fac02ac42f842, skills/open-code-review-delegate.

    line 21
  2. Very specific:

    Use only ocr delegate with the active host session.

    line 23
  3. Distinctive:

    Never publish findings, commit, merge or deploy without the user's authorization.

    line 26
  4. Distinctive:

    Use git directly based on the mode/ref info from Step 1:

    line 66
  5. Very specific:

    Create a checklist containing every reviewable_files entry.

    line 88
  6. Very specific:

    Use (path, status) as the checklist identity.

    line 90
  7. Very specific:

    Before reporting, verify that every previewed file is accounted for.

    line 114
  8. Distinctive:

    If the user requested "review and fix":

    line 126
  9. Distinctive:

    Do not silently truncate the source file.

    line 167
  10. Distinctive:

    If a faithful summary is not possible, omit the OCR background entirely and read the original material directly during the review.

    line 177

“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Open Code Review — Delegation Mode

Start met /code-audit. Upstream: alibaba/open-code-review at 23992511c8876f51c1a31e52938fac02ac42f842, skills/open-code-review-delegate. Use only ocr delegate with the active host session. Do not configure an API provider, switch models, or run ocr review/ocr scan as a fallback. Installation is not review evidence. Keep source, secrets and personal data on your own Claude seat. Never publish findings, commit, merge or deploy without the user's authorization. Compare the preview with git diff --name-status and untracked files. Review dependency manifests and tests even when OCR excludes them by default. Report coverage against the Git inventory, not only OCR's filtered list. A partial review never establishes that a release is safe to merge.

A skill for performing AI code review where OCR provides deterministic engineering (file filtering, rule resolution) and the host agent performs the actual review using its own intelligence and tools.

Workflow

Step 1: Preview — Determine What to Review

ocr delegate preview --format json [--from <ref> --to <ref>] [--commit <hash>] [--exclude <patterns>]

This outputs:

  • mode (workspace / range / commit)
  • from / to / commit / merge_base — ref metadata for constructing git commands
  • Reviewable file list — paths, status, insertions/deletions
  • Excluded files — with exclusion reason

Common invocations:

ScenarioCommand
Workspace changesocr delegate preview
Branch comparisonocr delegate preview --from main --to feature
Single commitocr delegate preview -c abc123

Step 2: Get Rules for Files

ocr delegate rule --format json <path1> <path2> ...

Pass the reviewable file paths from Step 1. Output is grouped by rule content — files sharing the same rule appear under one group, avoiding repetition.

Step 3: Get Diffs

Use git directly based on the mode/ref info from Step 1:

Range mode (merge_base provided in preview output):

git diff <merge_base>..<to> -- <path>

Commit mode:

git show <commit> -- <path>

Workspace mode:

# Tracked files
git diff HEAD -- <path>
# New untracked files — read directly (entire file is new code)
cat <path>

Step 4: Review Each File

Create a checklist containing every reviewable_files entry. For each reviewable file:

Use (path, status) as the checklist identity. Workspace mode can report the same path twice when a staged deletion is followed by an untracked recreation.

  1. Get its diff (Step 3)
  2. Consult its Rule Group (from Step 2) for the review checklist
  3. Conduct a thorough review, using appropriate context tools as needed
  4. Mark the file reviewed, or skipped with a concrete reason

For large changes, review in bounded batches grouped by shared rules and diff size. Do not stop after finding the first high-severity issue.

Step 5: Format Output

Each comment must follow this structure:

FieldTypeRequiredDescription
pathstringyesRelative file path
contentstringyesReview comment describing the issue
start_lineintegernoStart line in the new file
end_lineintegernoEnd line in the new file
categoryenumnobug, security, performance, maintainability, test, style, documentation, other
severityenumnocritical, high, medium, low

Step 6: Classify and Report

Before reporting, verify that every previewed file is accounted for. Include total_files, reviewed_files, skipped_files, and coverage_rate in the summary. A skipped file must include its reason.

Group findings by severity:

  • Critical/High: Bugs, security issues, data loss risks — always report
  • Medium: Performance concerns, error handling gaps, maintainability issues — report with context
  • Low: Style nits, minor suggestions — report only if clearly valuable

Discard likely false positives silently.

Step 7: Fix (Optional)

If the user requested "review and fix":

  • Apply High/Critical fixes directly
  • Describe Medium fixes that require manual intervention
  • Skip Low-priority items unless trivial

Sub-commands Reference

CommandPurpose
ocr delegate previewWhich files to review + mode/ref metadata
ocr delegate rule <path...>Review rules grouped by content

Shared Flags

FlagDescription
--from <ref>Source ref for range mode
--to <ref>Target ref for range mode
-c, --commit <hash>Single commit mode
--repo <path>Repository root (default: cwd)
--rule <path>Custom rule.json path
--exclude <patterns>Comma-separated exclude patterns
-b, --background <text>Business context
-B, --background-file <path>Business context from Markdown file (takes precedence over -b)
-f, --format <text|json>Output format; use json for agent integrations

Gotchas

  • No LLM needed on OCR side — delegation mode never calls an LLM. All intelligence comes from the host agent.
  • Rules are grouped — Files sharing the same rule are grouped together in the output. You can pass any number of paths per call; for large changes, fetch rules per-batch as you review.
  • Working directory matters — ocr delegate operates on the Git repo at the current directory. Use --repo /path to override.
  • Untracked files in workspace mode — preview includes untracked files. For these, read the file directly instead of using git diff.
  • Background context — pass --background to preview when you have requirement context; it appears in the output for your reference during review.
  • Coverage is mandatory — every reviewable_files entry must end as reviewed or explicitly skipped; do not silently omit files.

Recovering Oversized Background Context

--background-file has two independent limits. The raw file must not exceed 1 MiB, and the sanitized content must not exceed 8000 characters. Either condition aborts the command. When the command reports either limit:

  1. Do not silently truncate the source file.
  2. Summarize the original material while preserving its requirements, constraints, acceptance criteria, and other review-critical details.
  3. Retry the affected command by passing the summary as one shell-safe argument (for example, use a quoted/escaped argument produced by the host shell, or write it to a new size-bounded file and pass that file). Do not place untrusted summary text directly in a double-quoted shell template; $(), backticks, quotes, and variable references can still be evaluated. Omit the original --background-file so the CLI does not reload the same oversized file and fail again.
  4. If a faithful summary is not possible, omit the OCR background entirely and read the original material directly during the review.

Troubleshooting CLI Version Compatibility

The --format flag is available in ocr v1.9.0 and later. The Skill and the installed CLI can be updated independently. If a requested preview or rule command with --format json fails specifically with unknown flag: --format, rerun it without the flag and use text output for the rest of the delegation run. Preserve the explicit mode, ref, file, and rule information from that output; do not parse text output as JSON or invent missing schema fields. Do not retry without the flag for any other error; report it and stop the affected workflow.

The host-agent Skill may consume the equivalent text output to complete its review checklist. Programmatic integrations that require schema_version or other JSON fields must require a JSON-capable CLI instead: verify with ocr --version and upgrade when necessary:

npm install -g @alibaba-group/open-code-review

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.